小渣渣学习笔记 python day62【pandas】

Series

import pandas as pd
import numpy as np
s = pd.Series(np.random.randn(5),index=['a','b','c','d','e']) #创建序列Series
s 

a 1.172374
b 1.465648
c 0.116028
d -1.398484
e -0.517570
dtype: float64

s.index #获取序列索引

Index(['a', 'b', 'c', 'd', 'e'], dtype='object')

pd.Series(np.random.randn(6)) #随机数序列， 没有索引

0 0.957065
1 0.961984
2 -0.892521
3 -0.301281
4 0.400246
5 -0.220098
dtype: float64

d = {'b': 1, 'a': 0, 'c': 2}
pd.Series(d) #按字典创建序列

b 1
a 0
c 2
dtype: int64

d = {'a': 0., 'b': 1., 'c': 2.}
pd.Series(d)

a 0.0
b 1.0
c 2.0
dtype: float64

pd.Series(d,index=['b','c','d','a'])

b 1.0
c 2.0
d NaN
a 0.0
dtype: float64

pd.Series(5.,index=['a','b','c','d','e']) #创建值相同的序列

a 5.0
b 5.0
c 5.0
d 5.0
e 5.0
dtype: float64

s

a 1.172374
b 1.465648
c 0.116028
d -1.398484
e -0.517570
dtype: float64

s[0] #取第一个

1.1723744552417563

s[:3] #切片0-3

a 1.172374
b 1.465648
c 0.116028
dtype: float64

s[s>s.median()] #取大于中值的值

a 1.172374
b 1.465648
dtype: float64

s[[4,3,1]] #分别取索引是 4,3,1的值

e -0.517570
d -1.398484
b 1.465648
dtype: float64

np.exp(s) #指数，以e（约等于2.71828）为底的指数，相当于 print（2.71828**1.172374）

a 3.229652
b 4.330347
c 1.123028
d 0.246971
e 0.595967
dtype: float64

s.dtype #series 的类型

dtype('float64')

s.array

[ 1.1723744552417563, 1.4656476813208912, 0.11602825821369737,
-1.3984844654860116, -0.5175695557698142]
Length: 5, dtype: float64

s.to_numpy() #Series 转成ndarray

array([ 1.17237446, 1.46564768, 0.11602826, -1.39848447, -0.51756956])

Series 就像字典一样可以取值，设置值

s['a'] #取索引是a的元素

1.1723744552417563

s['e'] #取索引是e的元素

-0.5175695557698142

s #打印s

a 1.172374
b 1.465648
c 0.116028
d -1.398484
e -0.517570
dtype: float64

'e' in s #判断e是否在s中

True

'f' in s #f不在序列S中

False

s.get('a') #获取索引是a的值

1.1723744552417563

s.get('f',np.nan) #获取索引是f的值，不存在就返回NAN

nan

矢量运算

s+s #相加

a 2.344749
b 2.931295
c 0.232057
d -2.796969
e -1.035139
dtype: float64

s*2 #相乘

a 2.344749
b 2.931295
c 0.232057
d -2.796969
e -1.035139
dtype: float64

np.exp(s) #求自然常数e的指数

a 3.229652
b 4.330347
c 1.123028
d 0.246971
e 0.595967
dtype: float64

name属性

s1 = pd.Series(np.random.randn(5),name='aaa')
s1

0 1.447934
1 -0.499374
2 2.641901
3 0.131682
4 0.448031
Name: aaa, dtype: float64

s1.name

'aaa'

s2 = s1.rename('bbb') ###
s2.name

'bbb'

s2 #s1 和 s2  属于不同的对象

0 1.447934
1 -0.499374
2 2.641901
3 0.131682
4 0.448031
Name: bbb, dtype: float64

DataFrame

d = {'one':pd.Series([1,2,3.],index = ['a','b','c']),'two':pd.Series([1.,2.,3.,4.],index=['a','b','c','d'])}
df = pd.DataFrame(d)
df  #DataFrame的创建，input 的d是多个Series

	one	two
a	1.0	1.0
b	2.0	2.0
c	3.0	3.0
d	NaN	4.0

pd.DataFrame(d,index=['d','b','a'])   #index是行  ，行选择 dba 

	one	two
d	NaN	4.0
b	2.0	2.0
a	1.0	1.0

pd.DataFrame(d,index=['d','b','a'],columns=['two','three']) #列选择 two three 其中three没有内容

	two	three
d	4.0	NaN
b	2.0	NaN
a	1.0	NaN

df.index

Index(['a', 'b', 'c', 'd'], dtype='object')

df.columns

Index(['one', 'two'], dtype='object')

d = {'one':[1.,2.,3.,4.],'two':[4.,3.,2.,1.]}
pd.DataFrame(d)  #ndarray

	one	two
0	1.0	4.0
1	2.0	3.0
2	3.0	2.0
3	4.0	1.0

pd.DataFrame(d,index=['a','b','c','d'])

	one	two
a	1.0	4.0
b	2.0	3.0
c	3.0	2.0
d	4.0	1.0

data = np.zeros((2,),dtype=[('A','i4'),('B','f4'),('C','a10')])
data[:] = [(1,2.,'Hello'),(2,3,'World')]
pd.DataFrame(data)

	A	B	C
0	1	2.0	b'Hello'
1	2	3.0	b'World'

pd.DataFrame(data,index=['first','second'])

	A	B	C
first	1	2.0	b'Hello'
second	2	3.0	b'World'

pd.DataFrame(data,columns=['C','A','B'])

	C	A	B
0	b'Hello'	1	2.0
1	b'World'	2	3.0

data2 = [{'a':1,'b':2},{'a':5,'b':10,'c':20}]
pd.DataFrame(data2)

	a	b	c
0	1	2	NaN
1	5	10	20.0

pd.DataFrame(data2,index=['first','second'])

	a	b	c
first	1	2	NaN
second	5	10	20.0

pd.DataFrame(data2,columns=['a','b'])

	a	b
0	1	2
1	5	10

pd.DataFrame({('a','b'):{('A','B'):1,('A','C'):2},
              ('a','a'):{('A','C'):1,('A','B'):4},
              ('a','c'):{('A','B'):1,('A','C'):6},
              ('b','a'):{('A','C'):1,('A','B'):8},
              ('b','b'):{('A','D'):1,('A','B'):10}})

		a			b
		b	a	c	a	b
A	B	1.0	4.0	1.0	8.0	10.0
	C	2.0	1.0	6.0	1.0	NaN
	D	NaN	NaN	NaN	NaN	1.0